Learning on heterogeneous graphs using high-order relations

• Main Authors: Lee, See Hian, Ji, Feng, Tay, Wee Peng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2021
• Subjects: Engineering; Graph Neural Network; Heterogeneous Graph
• Online Access: https://hdl.handle.net/10356/147362
• Institution: Nanyang Technological University

A heterogeneous graph consists of different vertices and edges types. Learning on heterogeneous graphs typically employs meta-paths to deal with the heterogeneity by reducing the graph to a homogeneous network, guide random walks or capture semantics. These methods are however sensitive to the choic...